Unveiling the structure of wide flat minima in neural networks

Unveiling the structure of wide flat minima in neural networks

2 July 2021

Clarissa Lauditi

Enrico M. Malatesta

Gabriele Perugini

Papers citing "Unveiling the structure of wide flat minima in neural networks"

17 / 17 papers shown

Title
High-dimensional manifold of solutions in neural networks: insights from statistical physics Enrico M. Malatesta 46 4 0 20 Feb 2025
Do we really have to filter out random noise in pre-training data for language models? Jinghan Ru Yuxin Xie Xianwei Zhuang Yuguo Yin Zhihui Guo Zhiming Liu Qianli Ren Yuexian Zou 83 2 0 10 Feb 2025
The Persistence of Neural Collapse Despite Low-Rank Bias: An Analytic Perspective Through Unconstrained Features Connall Garrod Jonathan P. Keating 36 2 0 30 Oct 2024
Exact full-RSB SAT/UNSAT transition in infinitely wide two-layer neural networks B. Annesi Enrico M. Malatesta Francesco Zamponi 38 2 0 09 Oct 2024
A spring-block theory of feature learning in deep neural networks Chengzhi Shi Liming Pan Ivan Dokmanić AI4CE 40 1 0 28 Jul 2024
Engineered Ordinary Differential Equations as Classification Algorithm (EODECA): thorough characterization and testing Raffaele Marino L. Buffoni Lorenzo Chicchi Lorenzo Giambagli Duccio Fanelli 27 1 0 22 Dec 2023
Complex Recurrent Spectral Network Lorenzo Chicchi Lorenzo Giambagli L. Buffoni Raffaele Marino Duccio Fanelli 29 6 0 12 Dec 2023
Flat Minima in Linear Estimation and an Extended Gauss Markov Theorem Simon Segert 29 0 0 18 Nov 2023
Stochastic Gradient Descent-like relaxation is equivalent to Metropolis dynamics in discrete optimization and inference problems Maria Chiara Angelini A. Cavaliere Raffaele Marino F. Ricci-Tersenghi 53 5 0 11 Sep 2023
Regularization, early-stopping and dreaming: a Hopfield-like setup to address generalization and overfitting E. Agliari Francesco Alemanno Miriam Aquaro A. Fachechi 19 7 0 01 Aug 2023
Physics Inspired Approaches To Understanding Gaussian Processes Maximilian P. Niroomand L. Dicks Edward O. Pyzer-Knapp D. Wales 25 1 0 18 May 2023
Phase transitions in the mini-batch size for sparse and dense two-layer neural networks Raffaele Marino F. Ricci-Tersenghi 30 14 0 10 May 2023
Typical and atypical solutions in non-convex neural networks with discrete and continuous weights Carlo Baldassi Enrico M. Malatesta Gabriele Perugini R. Zecchina MQ 39 11 0 26 Apr 2023
Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry Fabrizio Pittorino Antonio Ferraro Gabriele Perugini Christoph Feinauer Carlo Baldassi R. Zecchina 204 24 0 07 Feb 2022
Binary perceptron: efficient algorithms can find solutions in a rare well-connected cluster Emmanuel Abbe Shuangping Li Allan Sly MQ 20 30 0 04 Nov 2021
Learning through atypical "phase transitions" in overparameterized neural networks Carlo Baldassi Clarissa Lauditi Enrico M. Malatesta R. Pacelli Gabriele Perugini R. Zecchina 26 26 0 01 Oct 2021
A spin-glass model for the loss surfaces of generative adversarial networks Nicholas P. Baskerville J. Keating F. Mezzadri J. Najnudel GAN 28 12 0 07 Jan 2021